Amplifiable construction method and system of customer service question-answering system based on artificial intelligence

Abstract

The invention provides an augmented construction method and system of a customer service question-answering system based on artificial intelligence. A question-answering report can be automatically generated by referring to a customer service question-answering text. The extensible construction method of the customer service question-answering system can also automatically generate an evaluation score according to the question-answering report. In addition, the amplifiable construction method of the customer service question-answering system can also determine whether to input the question-answering report into the AI model as a training set. The invention relates to an augmented construction method of a customer service question-answering system based on artificial intelligence. The construction method comprises the following steps: inputting a customer service question-answering text as a test set for testing an AI model; the AI model outputs a question and answer report based on the customer service question and answer text; an expert AI model outputs an evaluation score based on the question and answer report; and determining whether to input the question and answer report into the AI model as a training set based on the evaluation score.

Description

Technical Field

[0001] The present invention relates to an scalable construction method and a computer system for a customer service question and answer system based on artificial intelligence, and in particular to an scalable construction method and a computer system for a customer service question and answer system that can automatically generate a question and answer report and decide whether to input the question and answer report into an AI model as a training set. Background Art

[0002] With the rapid development of artificial intelligence (AI) technology, AI customer service systems have begun to be applied to various industries to provide automated customer service. AI customer service systems are mainly based on natural language processing (NLP) and machine learning (ML) technologies, which can simulate the interaction methods of human customer service representatives and automatically respond to customer inquiries. However, once the traditional AI customer service system completes the initial training, if it is not further updated and adjusted, the quality and accuracy of the system's answers will not be further improved.

[0003] In traditional models, the training of AI customer service systems usually relies on established data, which includes manually annotated conversation samples. This approach is effective in establishing basic conversation capabilities in the early stages, but it ignores the changes in customer needs and conversation context over time. Once trained, these systems often lack the ability to continue learning and cannot adapt to new customer inquiries or changing market needs.

[0004] In addition, traditional AI customer service systems perform poorly when dealing with unknown or rare questions, and are often unable to give appropriate responses due to a lack of sufficient training data. This limitation not only reduces customer satisfaction, but also limits the potential for the application of AI systems in more complex and changing scenarios. To overcome these challenges, it is necessary to develop more advanced AI customer service systems that can continuously improve their dialogue processing capabilities and answer quality through continuous learning and rapid data analysis. Summary of the invention

[0005] The main purpose of the present invention is to provide an expandable construction method of a customer service question and answer system based on artificial intelligence and a computer system thereof, which can automatically generate a question and answer report by referring to a customer service question and answer text.

[0006] Another object of the present invention is to provide an expandable construction method of an artificial intelligence-based customer service question-and-answer system and its computer system, which can automatically generate an evaluation score based on a question-and-answer report and decide whether to input the question-and-answer report into an AI model as a training set.

[0007] To achieve the above-mentioned purpose, the present invention provides an expandable construction method of a customer service question-and-answer system based on artificial intelligence, the construction method comprising:

[0008] (A) Input a customer service question and answer text as a test set to test an AI model;

[0009] (B) The AI ​​model outputs a Q&A report based on the customer service Q&A text;

[0010] (C) an expert AI model outputs an evaluation score based on the question and answer report; and

[0011] (D) Based on the evaluation score, decide whether to input the question and answer report into the AI ​​model as a training set.

[0012] The present invention provides a computer system, comprising:

[0013] one or more processors;

[0014] A memory is coupled to one or more processors, and the memory stores one or more programs. When the one or more programs are executed by one or more processors, the one or more processors implement an expandable construction method of an artificial intelligence-based customer service question-answering system, including:

[0015] (A) Input a customer service question and answer text as a test set to test an AI model;

[0016] (B) the AI ​​model outputs a question-and-answer report based on the customer service question-and-answer text;

[0017] (C) an expert AI model outputs an evaluation score based on the question and answer report; and

[0018] (D) Based on the evaluation score, decide whether to input the question and answer report into the AI ​​model as a training set.

[0019] The features, advantages, or similar expressions mentioned in this specification do not mean that all features and advantages that can be achieved by the present invention should be included in any single specific embodiment of the present invention. Instead, it should be understood that the expressions related to features and advantages mean that the specific features, advantages, or characteristics described in conjunction with the specific embodiment are included in at least one specific embodiment of the present invention. Therefore, the discussion of features and advantages, and similar expressions in this specification is related to the same specific embodiment, but it is not necessary.

[0020] These features and advantages of the present invention may be more clearly understood by referring to the following description and the appended claims or by utilizing the embodiments of the present invention as set forth below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The present invention and its features, appearance and advantages will become more apparent by reading the detailed description of non-limiting embodiments with reference to the following drawings. The same reference numerals indicate the same parts in all the drawings. The drawings are not drawn to scale, and emphasis is placed on illustrating the subject matter of the present invention.

[0022] Figure 1 A method flow chart of an expandable construction method of a customer service question-and-answer system based on artificial intelligence in a preferred embodiment of the present invention;

[0023] Figure 2 is a schematic diagram of an exemplary computer system / server suitable for implementing embodiments of the present invention;

[0024] Among them, 12 is a computer system / server, 14 is an external device, 16 is a processor, 18 is a bus, 20 is a network adapter, 22 is an I / O interface, 28 is a memory, 30 is a random access memory (RAM), 32 is a cache memory, 34 is a storage system, 40 is a program / utility, and 42 is a program module. DETAILED DESCRIPTION

[0025] In order to make the description of the disclosed content more detailed and complete, the following is an illustrative description of the implementation and specific embodiments of the present case; however, this is not the only form of implementing or using the specific embodiments of the present invention. The implementation covers the features of multiple specific embodiments and the method steps and sequences used to construct and operate these specific embodiments. However, other specific embodiments can also be used to achieve the same or equal functions and step sequences.

[0026] It should be noted that, unless otherwise specified, all functions described herein may be implemented in hardware or as software instructions that enable a computer to perform predetermined operations, wherein the software instructions are implemented in a computer-readable storage medium, such as RAM, a hard drive, flash memory, or other types of computer-readable storage media known to those skilled in the art. In some embodiments, the predetermined operations of the computer are performed by a processor, such as a computer, or a program code such as a computer program code, software, firmware, and in some embodiments, by an integrated circuit encoded to perform these functions. In addition, it should be understood that the various operations described herein as being performed by a user may be performed manually by the user, or may be performed automatically with or without instructions provided by the user.

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] It should be noted that the terminals involved in the embodiments of the present invention may include but are not limited to mobile phones, personal digital assistants (PDAs), wireless handheld devices, wireless Internet access devices, personal computers, portable computers, tablet computers, MP3 players, MP4 players, wearable devices (for example, smart glasses, smart watches, smart bracelets, etc.), mobile phones, smart phones, landline smart phones, etc.

[0029] Figure 1 The flowchart of the method for constructing an expandable customer service question-and-answer system based on artificial intelligence in a preferred embodiment of the present invention is as follows. Figure 1 As shown, it includes:

[0030] Step 101, input a customer service question and answer text as a test set to test an AI model.

[0031] Step 102: The AI ​​model outputs a question and answer report based on the customer service question and answer text.

[0032] Step 103: an expert AI model outputs an evaluation score based on the question and answer report.

[0033] Step 104: Based on the evaluation score, decide whether to input the question and answer report into the AI ​​model as a training set.

[0034] It should be noted that the execution entity of steps 101 to 104 may be an application located in the local terminal, or may be a functional unit such as a plug-in or software development kit (SDK) set in the application located in the local terminal, or may be a processing engine located in a network-side server, and this embodiment does not specifically limit this.

[0035] It is understandable that the application may be an application program (nativeApp) installed on the terminal, or may also be a webpage program (webApp) of a browser on the terminal, which is not limited in this embodiment.

[0036] Before step 101, it should be understood that in order to initially train the AI ​​model capable of answering customer service questions, some data may be provided to the AI ​​model as training data for learning and training. The training data may include, for example:

[0037] 1. Past customer service conversation records: This includes actual questions and answers from past customer service exchanges, which can be obtained from the company's customer service database. Its advantage is that it can provide real-world question and answer examples, which helps the model understand customer needs in specific areas.

[0038] 2. Frequently Asked Questions (FAQs): These are standardized answers to common questions, usually found on company websites. Their advantage is that they provide structured and precise information, which is very helpful for AI models to understand common problems.

[0039] 3. Customer service guides and internal training materials: This includes the company’s policies, procedures, product information, etc. The advantage is that it helps the AI ​​model understand how the company operates and the details of its products / services.

[0040] 4. Social media and forum posts: Such as questions and comments from customers on social media and online forums. The advantage is that it provides more extensive and informal conversation samples, which helps to understand the user's tone and word habits.

[0041] It should be understood that the training data in the present invention is not limited thereto.

[0042] After collecting the above training data, the AI ​​model in the customer service question and answer system of the present invention can be subjected to a common AI model initial training process, for example, including:

[0043] 1. Data preprocessing: Clean the collected data, including removing irrelevant information, correcting errors, standardizing the format, etc. Perform natural language processing steps such as word segmentation and part-of-speech tagging on the text.

[0044] 2. Feature extraction: Extract useful features from the text, such as keywords, sentence structure, emotional tendencies, etc.

[0045] 3. Choose an appropriate machine learning model: Choose a suitable model according to your needs, such as decision tree, support vector machine (SVM), deep learning model, etc.

[0046] 4. Training model: Using preprocessed data to train the model may require multiple rounds of iterative training.

[0047] 5. Evaluation and fine-tuning: Use the test set to evaluate the effectiveness of the model, and adjust and optimize based on the results.

[0048] 6. Actual application testing: Test the performance of the AI ​​model in a real environment and further fine-tune it.

[0049] The above is the common initial training process of AI models, which will not be elaborated in this article.

[0050] In step 101 of the present invention, a customer service question and answer text is input as a test set to test an AI model. The customer service question and answer text may be a set of customer service question and answer texts selected or created, which represent typical customer consultations and standard answers. For example, texts may be selected from existing customer service records, or simulated conversations may be written by professionals. In other embodiments, the customer service question and answer text may also use customer service communication records in a public database to improve the scope of application and flexibility of the AI ​​model.

[0051] To help you understand, the following is an example of a customer service Q&A text, in which the customer service staff is Mr. Chen, the caller is Mr. Zhang, and the content of the customer service Q&A text is as follows: Mr. Chen: Hello, this is the customer service center, I am Mr. Chen. How can I help you?

[0052] Mr. Zhang: Hello, my name is Mr. Zhang. I am very dissatisfied with the quality of a product I recently ordered.

[0053] Mr. Chen: I'm sorry to hear that you encountered such a problem, Mr. Zhang. Could you please describe in detail what the specific problem is?

[0054] Mr. Zhang: The appearance of the product is completely different from the description on the website when I ordered it. I ordered the blue one, but the one I received is green, and the size is much smaller. Your quality management is very problematic.

[0055] Mr. Chen: I see. We are very sorry for the inconvenience. To resolve this issue, we can arrange a return or exchange service for you. In addition, as an apology, we will provide you with a discount coupon.

[0056] Mr. Zhang: That sounds good. I hope it can be resolved smoothly this time.

[0057] Mr. Chen: Of course, Mr. Zhang. We will deal with this matter as soon as possible. Thank you for your understanding and patience.

[0058] Mr. Zhang: OK, thank you for your help.

[0059] In step 102, the AI ​​model outputs a question and answer report based on the customer service question and answer text. The AI ​​model analyzes the test set, identifies the patterns of questions and answers, and then generates a report describing its processing and response strategies for each question and answer. For example, in one embodiment of the present invention, the AI ​​model can output a question and answer report based on the customer service question and answer text and a list of items.

[0060] The items included in the item list are used to standardize the format and content of the Q&A report. For example, each item in the item list may include: a summary of the customer's question, a method to solve the problem, captured keywords, how to respond to the customer in a comfortable manner, the customer's emotional state and level, reminders to customer service personnel, and the main intention of the customer's question, one or a combination thereof, but the present invention is not limited to this. It should be understood that by requiring the AI ​​model to output a Q&A report based on the item list, each Q&A report can include one or a combination of the items in the item list, which is helpful for outputting an evaluation score for the Q&A report in the subsequent steps.

[0061] To help understand, an exemplary Q&A report is provided below. The Q&A report is based on the customer service Q&A text provided above, and is output according to the specifications of the project list. The content of the Q&A report in this example is as follows, but it should be understood that it is not intended to limit the present invention:

[0062] Summary of customer's problem:

[0063] •The product ordered by Mr. Zhang did not match the description on the website in terms of appearance and size. The color of the product received (green) was different from the color ordered (blue), and the size was smaller than expected.

[0064] Solution to the problem:

[0065] • Provide return and exchange service, and give Mr. Zhang a discount coupon as an apology.

[0066] Extracted keywords:

[0067] • Product quality

[0068] • Description does not match

[0069] •Returns and Exchanges

[0070] • Discount coupons

[0071] How to respond to customers in a comfortable way:

[0072] "Mr. Zhang, we take your feedback very seriously and are sorry for the product problem. We will process your return or exchange immediately and provide a discount coupon as our sincere apology. Your satisfaction is our greatest pursuit, please rest assured that we will ensure that this problem is properly resolved."

[0073] Customer emotional state and degree:

[0074] •Emotional language: "very dissatisfied"

[0075] • Emotional level: A (highly excited)

[0076] Reminders to customer service staff:

[0077] •Listen carefully to the problems described by the customer and avoid interrupting or ignoring the customer's requests.

[0078] •Express empathy and apology, even if the issue may not have been directly caused by customer service.

[0079] •Provide clear solutions and ensure clients understand and are satisfied with them.

[0080] •Maintain a professional attitude, even with emotional customers.

[0081] The main purpose of the customer's question:

[0082] • Mr. Zhang hopes to get more than just a solution to the product problem, he also hopes to be taken seriously and respected by the company. By providing return and exchange services and discount coupons, the company can show its awareness of customer inconvenience and its willingness to take responsibility.

[0083] In step 103, an expert AI model outputs an evaluation score based on the question and answer report. In the present invention, the expert AI model can also evaluate the question and answer report based on a pre-set combination of evaluation conditions, and then output an evaluation score. Among them, the combination of evaluation conditions can be: response speed, resolution efficiency, communication skills, customer satisfaction, compliance with processes and policies and other items, as a reference benchmark for scoring. Among them, response speed: that is, the customer service staff should respond to customer inquiries within a specific time. Resolution efficiency: that is, evaluating the speed and efficiency of customer service personnel in solving problems. Communication skills: that is, including tone, word choice, listening ability, etc. Customer satisfaction: that is, evaluating customer satisfaction through surveys or direct feedback. Compliance with processes and policies: that is, evaluating whether customer service personnel act in accordance with the processes and policies prescribed by the company. It should be understood that the present invention is not limited to this combination of evaluation conditions for expert AI models.

[0084] In the present invention, the expert AI model can be an external artificial intelligence model, such as Google Cloud Natural Language API, IBM Watson Assistant, OpenAI's GPT-series, Amazon Comprehend, or Microsoft Azure Cognitive Services, etc. In addition, the expert AI model in the present invention can also be a model of an offline self-built server, such as Meta's Llama 2, etc.

[0085] To facilitate understanding, the following provides an example of an evaluation condition combination, but it should be understood that it is not intended to limit the present invention. The following example provides scoring rules for each condition and instructions for judging according to the scoring rules:

[0086] Each question is 20 points, total score is 100 points

[0087] Response speed

[0088] Scoring Rules

[0089] 20 points: Respond to customer inquiries within a specified time (e.g. 5 minutes)

[0090] 15 points: Respond to customer inquiries within the specified time, but remind the customer to wait

[0091] 10 points: Responding to customer inquiries beyond the stipulated time

[0092] According to the above scoring rules, it is impossible to directly judge from the conversation whether Mr. Chen's response speed meets the requirements within the specified time. However, judging from the fluency of the conversation, he responded to the customer's inquiry within the specified time, and 20 points can be given.

[0093] Rating: 20 points

[0094] Solution efficiency

[0095] Scoring rules 20 points: Solve the problem within a time that satisfies the customer (e.g. 5 minutes)

[0096] 15 points: Solve the problem within a time acceptable to the customer

[0097] 10 points: The problem is solved within the acceptable time for the customer

[0098] According to the above scoring rules, Mr. Chen quickly proposed a solution (return and exchange service and discount coupons), which shows efficient problem-solving ability. According to the content of the conversation, Mr. Chen solved the problem within a time that satisfied the customer.

[0099] Rating: 20 points

[0100] Communication skills

[0101] Scoring Rules

[0102] 20 points: Friendly and polite tone, clear and understandable language, strong listening skills

[0103] 15 points: Friendly and polite tone, clear language, average listening skills

[0104] 10 points: unfriendly and impolite tone, unclear language, poor listening skills

[0105] According to the above scoring rules: Mr. Chen showed a friendly and polite attitude throughout the conversation, his language was clear and easy to understand, and he demonstrated good listening skills.

[0106] Rating: 20 points

[0107] Customer Satisfaction

[0108] Scoring Rules

[0109] 20 points: The customer is satisfied with the service provided by the customer service staff

[0110] 15 points: The customer is basically satisfied with the service provided by the customer service staff

[0111] 10 points: The customer is dissatisfied with the service provided by the customer service staff

[0112] Judging according to the above scoring rules: From the conversation, it can be seen that Mr. Zhang is satisfied with the solution provided by Mr. Chen and thanks him for his help.

[0113] Rating: 20 points

[0114] Comply with procedures and policies

[0115] Scoring Rules

[0116] 20 points: Full compliance with company-mandated processes and policies

[0117] 15 points: Basically complies with the company's procedures and policies, but there are some omissions

[0118] 10 points: Failure to follow company-mandated procedures and policies

[0119] Judging by the above scoring rules: During the conversation, the customer service representative surnamed Chen seemed to have only partially complied with the company's procedures and policies, including the proactive provision of compensation measures, which required the approval of the supervisor before implementation. Therefore, 4 points were deducted to indicate strict compliance with company regulations.

[0120] Rating: 16 points

[0121] Total score: 96 points (meets the standard)

[0122] In step 104, based on the evaluation score, decide whether to input the question and answer report into the AI ​​model as a training set. Further, assuming that the evaluation score ranges from 0 to 100 points, if the predetermined standard is met (for example, above 80 points), the question and answer report will be included in the training set of the AI ​​model to further improve its performance. If the predetermined standard is not met, the question and answer report will be discarded and not included in the training set of the AI ​​model. In other embodiments of the present invention: in the case of low scores (for example, below 59 points), the question and answer report can be used to diagnose and improve specific aspects of the AI ​​model. Alternatively, a medium score (for example, between 60 and 79 points) may result in part of the data being used for training, but it also needs to be further reviewed manually by human experts. That is, different follow-up actions can be set for different levels of scoring.

[0123] From the above description, it can be seen that the expandable construction method of the customer service question and answer system based on artificial intelligence proposed in the present invention can automatically generate a question and answer report by referring to a customer service question and answer text. The expandable construction method of the customer service question and answer system of the present invention can also automatically generate an evaluation score based on the question and answer report. In addition, the expandable construction method of the customer service question and answer system of the present invention can also determine whether to input the question and answer report into the AI ​​model as a training set. Compared with traditional AI customer service systems, the expandable construction method of the customer service question and answer system of the present invention can continuously improve its dialogue processing capabilities and answer quality through continuous learning and rapid data analysis.

[0124] Figure 2 is a schematic diagram of an exemplary computer system / server suitable for implementing embodiments of the present invention. Figure 2 The computer system / server 12 shown is merely an example and should not bring any limitation to the functionality and scope of use of embodiments of the present invention.

[0125] like Figure 2 As shown, computer system / server 12 is in the form of a general purpose computing device. Components of computer system / server 12 may include, but are not limited to: one or more processors (processing units) 16, memory 28, and bus 18 connecting various system components (including memory 28 and processor 16).

[0126] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration communication port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0127] Computer system / server 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer system / server 12, including volatile and non-volatile storage media, removable and non-removable storage media.

[0128] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer system / server 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 2not shown, usually called a "hard drive"). Although Figure 2 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0129] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28. Such program modules 42 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0130] The computer system / server 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays, etc.), one or more devices that enable a user to interact with the computer system / server 12, and / or any device that enables the computer system / server 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via input / output (I / O) interfaces 22. Furthermore, the computer system / server 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. Figure 2 As shown, the network adapter 20 communicates with other modules of the computer system / server 12 via the bus 18. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in conjunction with the computer system / server 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0131] The processor 16 executes various functional applications and data processing by running the programs stored in the memory 28, such as implementing Figure 1 The method in the illustrated embodiment.

[0132] The present invention also discloses a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, will implement the following Figure 1 The method in the illustrated embodiment.

[0133] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical memory device, a magnetic memory device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that includes or stores a program that may be used by or in combination with an instruction execution system, device, or device.

[0134] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to: electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0135] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0136] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0137] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only exemplary, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation.

[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist as a separate entity, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0140] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: a flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0141] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for constructing an scalable customer service question-answering system based on artificial intelligence, characterized in that: The construction method includes: (A) Input a customer service question and answer text as a test set to test an AI model; (B) the AI ​​model outputs a question-and-answer report based on the customer service question-and-answer text; (C) an expert AI model outputs an evaluation score based on the question and answer report; and (D) Based on the evaluation score, decide whether to input the question and answer report into the AI ​​model as a training set.

2. The method for constructing an scalable customer service question-and-answer system based on artificial intelligence according to claim 1, characterized in that: Step (B) also includes the AI ​​model outputting the question and answer report based on the customer service question and answer text and a list of items.

3. The method for constructing an scalable customer service question-and-answer system based on artificial intelligence according to claim 2, characterized in that: The list of items includes: a summary of the customer's problem, methods for solving the problem, captured keywords, how to respond to the customer in a comfortable manner, the customer's emotional state and level, reminders for customer service staff, and one or a combination of the main intentions of the customer's problem.

4. The method for constructing an artificial intelligence-based customer service question-answering system that can be expanded according to claim 1, characterized in that: Step (C) also includes the expert AI model outputting an evaluation score based on the question and answer report and an evaluation condition combination.

5. The method for constructing an expandable customer service question-and-answer system based on artificial intelligence according to claim 4, characterized in that: The combination of evaluation criteria includes: response speed, resolution efficiency, communication skills, customer satisfaction, compliance with procedures and policies, or a combination thereof.

6. A computer system, characterized in that: include: one or more processors; A memory is coupled to the one or more processors, and the memory stores one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement an expandable construction method of an artificial intelligence-based customer service question-answering system, including: (A) Input a customer service question and answer text as a test set to test an AI model; (B) the AI ​​model outputs a question-and-answer report based on the customer service question-and-answer text; (C) an expert AI model outputs an evaluation score based on the question and answer report; and (D) Based on the evaluation score, decide whether to input the question and answer report into the AI ​​model as a training set.

7. A computer system according to claim 6, characterized in that: When the one or more processors implement an expandable construction method of an artificial intelligence-based customer service question and answer system, it also includes the AI ​​model outputting the question and answer report based on the customer service question and answer text and according to a list of items.

8. A computer system according to claim 7, characterized in that: When the one or more processors implement an expandable construction method of an artificial intelligence-based customer service question-and-answer system, the project list includes: a summary of the customer's question, a method for solving the problem, extracted keywords, how to respond to the customer in a comfortable manner, the customer's emotional state and level, reminders for customer service personnel, and one or a combination of the main intentions of the customer's question.

9. A computer system according to claim 6, characterized in that: When the one or more processors implement an expandable construction method of an artificial intelligence-based customer service question-and-answer system, the expert AI model also outputs an evaluation score based on the question-and-answer report and according to an evaluation condition combination.

10. A computer system according to claim 9, characterized in that: When the one or more processors implement an expandable construction method of an artificial intelligence-based customer service question-and-answer system, the combination of evaluation conditions includes: response speed, resolution efficiency, communication skills, customer satisfaction, compliance with processes and policies, or one or a combination thereof.

Images